[None][feat] Add benchmark to DeepConf #8776
Conversation
|
/bot run --disable-fail-fast |
|
PR_Github #22984 [ run ] triggered by Bot. Commit: |
📝 WalkthroughWalkthroughThe pull request introduces benchmarking scaffolding to a DeepConf system by adding a dataset file, utility functions for answer parsing and prompt construction, comprehensive documentation, refactored voting logic with policy-driven task selection, and extended benchmarking capabilities to the generation runner with timing instrumentation and accuracy tracking. Changes
Sequence DiagramsequenceDiagram
participant Main as main()
participant Prep as prepare_prompt()
participant Run as run_scaffolding_llm()
participant Vote as majority_vote()
participant Extract as extract_answer_from_boxed()
participant Bench as BenchResult
Main->>Main: Load dataset from JSONL
Main->>Main: Select question by id
Main->>Prep: Prepare prompt with tokenizer
Prep-->>Main: Return formatted prompt
Main->>Run: Call with repeat_times, ground_truth
loop For repeat_times iterations
Run->>Vote: Select task via policy mapping
Vote-->>Run: Return (policy_dict, selected_task)
Run->>Extract: Extract answer from result
Extract-->>Run: Return parsed answer
Run->>Run: Compare with ground_truth
Run->>Bench: Accumulate per-policy stats
end
Run-->>Main: Return BenchResult with aggregated accuracy
Main->>Main: Print per-policy accuracy & median time
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes
Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Actionable comments posted: 2
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (5)
examples/scaffolding/contrib/DeepConf/brumo_2025.jsonl(1 hunks)examples/scaffolding/contrib/DeepConf/run_generation.py(7 hunks)examples/scaffolding/contrib/DeepConf/utils.py(1 hunks)tensorrt_llm/scaffolding/contrib/DeepConf/README.md(1 hunks)tensorrt_llm/scaffolding/contrib/DeepConf/deep_conf_utils.py(3 hunks)
🧰 Additional context used
📓 Path-based instructions (3)
**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Use only spaces, no tabs; indent with 4 spaces.
Files:
examples/scaffolding/contrib/DeepConf/utils.pytensorrt_llm/scaffolding/contrib/DeepConf/deep_conf_utils.pyexamples/scaffolding/contrib/DeepConf/run_generation.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.
Files:
examples/scaffolding/contrib/DeepConf/utils.pytensorrt_llm/scaffolding/contrib/DeepConf/deep_conf_utils.pyexamples/scaffolding/contrib/DeepConf/run_generation.py
**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).
Files:
examples/scaffolding/contrib/DeepConf/utils.pytensorrt_llm/scaffolding/contrib/DeepConf/deep_conf_utils.pyexamples/scaffolding/contrib/DeepConf/run_generation.py
🧠 Learnings (1)
📓 Common learnings
Learnt from: venkywonka
PR: NVIDIA/TensorRT-LLM#6029
File: .github/pull_request_template.md:45-53
Timestamp: 2025-08-27T17:50:13.264Z
Learning: For PR templates in TensorRT-LLM, avoid suggesting changes that would increase developer overhead, such as converting plain bullets to mandatory checkboxes. The team prefers guidance-style bullets that don't require explicit interaction to reduce friction in the PR creation process.
🧬 Code graph analysis (1)
examples/scaffolding/contrib/DeepConf/run_generation.py (4)
examples/scaffolding/contrib/DeepConf/utils.py (2)
equal_func(21-28)prepare_prompt(31-54)tensorrt_llm/scaffolding/worker.py (2)
TRTLLMWorker(134-250)init_with_new_llm(146-181)tensorrt_llm/scaffolding/math_utils.py (1)
extract_answer_from_boxed(14-53)tensorrt_llm/scaffolding/contrib/DeepConf/deep_conf_controller.py (2)
DeepConfOnlineMajorityVoteController(125-211)DeepConfOfflineMajorityVoteController(43-76)
🪛 LanguageTool
tensorrt_llm/scaffolding/contrib/DeepConf/README.md
[style] ~7-~7: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym.
Context: ...rated into existing serving frameworks. It achieves up to 99.9% accuracy on AIME 2...
(ENGLISH_WORD_REPEAT_BEGINNING_RULE)
🪛 markdownlint-cli2 (0.18.1)
tensorrt_llm/scaffolding/contrib/DeepConf/README.md
82-82: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🪛 Ruff (0.14.2)
examples/scaffolding/contrib/DeepConf/utils.py
41-41: String contains ambiguous ， (FULLWIDTH COMMA). Did you mean , (COMMA)?
(RUF001)
41-41: String contains ambiguous ， (FULLWIDTH COMMA). Did you mean , (COMMA)?
(RUF001)
tensorrt_llm/scaffolding/contrib/DeepConf/deep_conf_utils.py
120-120: Standard pseudo-random generators are not suitable for cryptographic purposes
(S311)
136-136: Standard pseudo-random generators are not suitable for cryptographic purposes
(S311)
examples/scaffolding/contrib/DeepConf/run_generation.py
73-73: Unused function argument: kwargs
(ARG001)
222-222: f-string without any placeholders
Remove extraneous f prefix
(F541)
|
PR_Github #22984 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #23030 [ run ] triggered by Bot. Commit: |
|
PR_Github #23030 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #23100 [ run ] triggered by Bot. Commit: |
|
PR_Github #23100 [ run ] completed with state |
3e8e1af to
11c8278
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #23309 [ run ] triggered by Bot. Commit: |
11c8278 to
3aad2b9
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #23330 [ run ] triggered by Bot. Commit: |
|
PR_Github #23309 [ run ] completed with state |
|
PR_Github #23330 [ run ] completed with state |
Signed-off-by: Dong Cao <docao@nvidia.com> Signed-off-by: FredricZ-2007 <226039983+fredricz-20070104@users.noreply.github.com>
Summary by CodeRabbit
New Features
Documentation
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...Provide a user friendly way for developers to interact with a Jenkins server.
Run
/bot [-h|--help]to print this help message.See details below for each supported subcommand.
run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]Launch build/test pipelines. All previously running jobs will be killed.
--reuse-test (optional)pipeline-id(OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.--disable-reuse-test(OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.--disable-fail-fast(OPTIONAL) : Disable fail fast on build/tests/infra failures.--skip-test(OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.--gpu-type "A30, H100_PCIe"(OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.--test-backend "pytorch, cpp"(OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.--add-multi-gpu-test(OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.--post-merge(OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".--detailed-log(OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.--debug(OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in thestage-listparameter to access the appropriate container environment. Note: Does NOT update GitHub check status.For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip testing for latest commit on pull request.
--comment "Reason for skipping build/test"is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.reuse-pipeline
reuse-pipelineReuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.